Skills
101,323 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Manage CI/CD pipeline schedules including create, list, update, delete, and run scheduled pipelines. Use when automating pipelines, setting up cron jobs, or managing scheduled builds. Triggers on schedule, scheduled pipeline, cron, pipeline schedule, automated build.
Official skill for recognizing handwritten text from images using ZhiPu GLM-OCR API. Supports various handwriting styles, languages, and mixed handwritten/printed content. Use this skill when the user wants to read handwritten notes, convert handwriting to text, or OCR handwritten documents.
Index and routing table for this repository's Go skills: maps a task to the skill that owns it, names the secondary skills worth loading alongside, and draws the boundary between skills whose triggers overlap. Use when it is unclear which Go skill applies, when a task spans several concerns at once, when two skills seem to cover the same ground, or when the user asks what Go skills are available or wants a project configured to load them. Trigger examples: "which skill should I use", "what Go skills do you have", "is this concurrency or performance", "set up the Go skills for this repo". Not for: a task that already maps cleanly to one skill — load that skill directly.
GoldRush CLI — terminal-first blockchain data tool with MCP support for Claude Desktop and Claude Code. Use this skill whenever the user wants to query blockchain data from the command line, stream DEX pairs or wallet activity in a terminal, set up GoldRush as an MCP tool provider, or run quick one-off queries without writing code (e.g., 'check a wallet balance', 'what's the gas price', 'search for a token'). Also use this when the user mentions 'goldrush' CLI commands, 'npx @covalenthq/goldrush-cli', or MCP integration with GoldRush. The CLI is the fastest path for ad-hoc blockchain lookups from the terminal. If the user needs programmatic API access in an application, use goldrush-foundational-api or goldrush-streaming-api instead. If the user needs pay-per-request access without an API key, use goldrush-x402 instead.
When the user wants to set up or analyze a Google Ads experiment, A/B test, ad variation test, campaign draft, split test, or bid strategy experiment. Also triggers on 'Google Ads experiments', 'campaign experiment', 'ad variation test', 'split test', 'test bid strategy', 'A/B test ads', 'test landing page', 'statistical significance', 'experiment setup', 'control vs treatment', 'uplift test', or 'test new campaign structure'. For ongoing keyword and ad copy optimization see google-ads-search. For bid strategy choices see google-ads-bidding.
Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any explicit ask to generate or edit with this model.
Turns a vague goal, idea, plan, or design into clear decisions and an actionable plan through scoped questioning. Use when the user asks to be grilled, to stress-test a plan or design, or to pin an idea down into decisions before building; not for generating new ideas or reviewing code.
Explain with empathy and transparency how Gupy's AI works in selection — what it analyzes (experience, skills), what it does not use to judge (sensitive data such as age, race, gender, name, location), who actually approves or rejects, and why there appears to be automatic rejection. ALWAYS trigger when the candidate asks about screening, robot/AI, bias in the profile, who decides who advances, suspects they were unfairly eliminated, or vents that they never pass a process — even without mentioning Gupy or AI. Do not trigger to review a profile, checklist, keywords, PDF upload, optimize for a specific job, or improve visibility (use analise-de-curriculo); nor for job search, application flow, or interview preparation.
Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235, [email protected]) — optimizes a harness genome against a SWE-bench-style slice manifest. $0 dry-run by default; `--run` is the explicit spend opt-in. Requires a metaharness repo checkout (`--repo` or $METAHARNESS_REPO) — without one it reports `checkout-required` with clone instructions. Degrades gracefully when metaharness is absent.
Entry skill for the Headless Ghidra YAML-first reverse-engineering pipeline. Use when the user asks to analyze, decompile, triage, resume, or iterate on a binary target with Ghidra/headless-ghidra. Reads artifacts/<target>/pipeline-state.yaml, routes P0–P4 phase skills, runs gate checks, and manages review pauses. Performs zero analysis work itself.
Make every click in a screen recording legible: add a brief visual emphasis on the cursor at each click and selection so viewers never lose the pointer. Use when the user says "highlight my clicks", "make the cursor visible", "viewers can't see where I'm clicking", "add click effects", or "emphasize the mouse actions".
Hostinger Hosting API for website management, order listing, datacenter selection, domain verification, free subdomains, databases, subdomains, parked domains, Node.js applications, and WordPress installs. Use when creating websites, listing hosting orders, choosing datacenters, verifying domain ownership, managing MySQL databases, adding subdomains or parked domains, deploying Node.js apps, or installing WordPress.
Remove AI-generated traces from text. Use when editing or reviewing text so it sounds more natural and human-written. A comprehensive guide based on Wikipedia's "signs of AI writing." Detects and fixes patterns such as inflated significance, promotional language, superficial -ing analyses, vague attribution, overused em dashes, rule of three, AI vocabulary, negative parallelisms, and excessive connective phrases.
Hyperliquid L1 reference for Dwellir endpoints: HyperEVM JSON-RPC, Info API proxy, gRPC L1 streaming, order book WebSocket, dedicated nodes, and trading patterns. Covers HyperCore trading layer, HyperEVM smart contracts (chain ID 999), market data queries, perpetuals metadata, spot markets, and best practices. Use when working with Hyperliquid, HYPE, HyperEVM, HyperCore, perpetual futures, order books, funding rates, or Hyperliquid trading through Dwellir. Triggers on mentions of hyperliquid, HYPE, HyperEVM, HyperCore, order book, perpetuals, funding rate, l2Book, l4Book, gRPC streaming, nanoreth, or hyperliquid trading.
Generate ONE reviewer-defensible, implementable research idea with a concrete method and falsification plan from a stated research direction. Use when the user asks for a research idea, novelty analysis, bottleneck diagnosis, or paper-shape suggestion. Skip code review, debugging, and unconstrained brainstorming without research context.
Image assistant - turn article/module content into uniform-style, low-text, highly readable 16:9 infographic prompts; first decide "how many images are needed + what each one covers", then compress the copy and metaphors, and finally output directly copyable image-generation prompts and iterate.
Image format conversion — PNG/JPG/WebP/GIF conversion, resizing, ICO icon generation, Base64 encoding. Use when the user wants to convert formats, change dimensions, or make a favicon. [Important] You must first read the skill source to get the correct command format; do not guess.
Discover and shape architecture improvement or simplification opportunities in hard-to-understand, hard-to-test, shallow, scattered, or over-coupled code. Use when the opportunity or interface shape still needs discovery, not for an already-decided bounded change.
Integrate Arcjet Guard into Python Claude Managed Agents — screen user.message with guard_events before sessions.events.send, and gate custom tools on agent.custom_tool_use with guard_custom_tool. Use when asked to add Arcjet to hosted Claude Managed Agents, anthropic beta sessions, rate limit custom tools, or block prompt injection on hosted sessions. Not Claude Agent SDK local query() / PreToolUse.
Integrate Arcjet Guard into Python Strands Agents — wrap authored @tool with guard_tool, and put guard_hooks on Agent(hooks=) for unwrapped / MCP tools via BeforeToolCallEvent.cancel_tool. Use when asked to add Arcjet to strands / strands-agents, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python strands, not JS @strands-agents/sdk.
Based on the case fact description, coordinates 8 atomic capabilities to generate a complete criminal judgment with standard formatting and rigorous argumentation. Covers the full process of fact finding, legal application, sentencing reasoning, and document output.
Interactive feature development workflow from idea to implementation. Creates requirements (EARS format), design documents, and implementation task lists. Use when creating feature specs, requirements documents, design documents, or implementation plans. Triggered by "kiro" or references to .kiro/specs/ directory.
Lead sources by use case with a data workspace delivery-ready templates - Apollo, LinkedIn Sales Navigator, a data workspace, Ocean.io, Openmart, and Local Directories. Use when choosing lead sources, building prospecting workflows, or setting up data enrichment.
Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.
LinkedIn Ads platform expertise. Audit campaigns, optimize targeting (job title, company, seniority, industry), creative strategy, Lead Gen Forms, conversion tracking, and ABM campaigns. Use when the user asks about LinkedIn advertising, B2B paid social, LinkedIn campaign optimization, Lead Gen Forms, Matched Audiences, or professional audience targeting.
When the user wants to reach developers on LinkedIn, create technical content for B2B audiences, or understand when LinkedIn beats Twitter. Trigger phrases include "LinkedIn," "LinkedIn for developers," "B2B developer marketing," "engineering managers," "reaching CTOs," or "technical LinkedIn content."
Use when references in a .bib file (often from /search-lit) should land in Zotero and Obsidian. Syncs them to the Zotero library, writes Obsidian literature notes and extracts cross-cutting concept notes once enough accumulate. A folder of PDFs is /obsidian-paper-vault.
Author, render, troubleshoot, and review Mermaid diagrams for documentation, architecture, processes, and technical communication. Use when a versionable diagram must communicate a defined audience job across a real renderer, including narrative, hierarchy, labels, legends, accessibility fallback, and uncertainty. Do not use for C4 level/model ownership, architecture decisions, or full accessibility conformance.
Create a futuristic, premium, clean dark-blue mesh-gradient design system across background rendering, hero shell, navigation, floating nodes, framed sections, CTAs, and motion. Use when the interface needs a near-black navy foundation, procedural blue mesh atmosphere, disciplined minimal structure, and infrastructural or planetary depth.
Convert local documents, remote document URLs, or web page URLs to Markdown. Uses a lightweight no-login endpoint out of the box by default; if a MinerU Token is configured, switches automatically to the standard API. Retains the archive tracing capability and supports Token self-checks and private deployment connection instructions. This skill should be used when the user needs PDF to Markdown, OCR, remote document conversion, web content extraction, table recognition, formula recognition, document conversion, image to text, or scanned document conversion.
AI-powered browser automation SDK for web scraping, testing, and workflow automation. Use when automating web browsers, extracting data from websites, testing web applications, or building web automation workflows. Supports both API key and AWS credential authentication.
Guide for implementing obsidian.nvim - a Neovim plugin for Obsidian vault management. Use when configuring, troubleshooting, or extending obsidian.nvim features including workspace setup, daily notes, templates, completion, pickers, and UI customization.
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to dashboard', 'data visualization'. Output is a single .xlsx. Scene-layer on officecli-xlsx: inherits every xlsx hard rule. DO NOT invoke for: a single budget tracker / one-sheet CSV-with-formatting (use xlsx), a 3-statement / DCF / LBO financial model (use financial-model), a weekly report with at most 1 chart and fewer than 10 rows (use xlsx).
Use for new frontend applications, dashboards, games, creative websites, hero sections, and visually driven UI from scratch, or when the user explicitly asks for a redesign/restyle/modernization. Builds from clean, airy, high-taste, readable image-generated concept design with section-specific references, faithful implementation, and browser testing.
Create or redesign enterprise AI, automation, security, and operations product pages that explain system boundaries, approvals, auditability, exceptions, and rollback. Use for dark cinematic heroes, hairline grids, metric pauses, expandable solution rows, case-study evidence, security proof, and qualified demo or waitlist handoffs.
Build an LLM evaluation and run it against the app, returning an Opik experiment with scores and its link. Picks a test suite with judge assertions or a dataset with metrics, sources cases from traces or synthetic data, scores heuristics-first then one-failure-mode judges, runs client-side via the SDK or server-side for prompt-only targets, and reads the scores back. Covers RAG evaluation, error analysis, writing and validating LLM judges against human labels, and auditing an existing eval pipeline. Use for "evaluate my agent", "measure quality", "build an eval", "write an LLM judge for hallucinations", "audit our evaluation pipeline", "how good is my RAG", "set up evals for this". Not for before/after on an existing suite (use compare), one regression case (use test), scoring production traffic (use online-eval), or the ship/hold decision (use verify).
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
